Update dependencies and pre-commit

Author: cjdsellers

Diff for: .pre-commit-config.yaml

@@ -3,7 +3,7 @@ repos:
   #  General checks
   ##############################################################################
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
       - id: fix-encoding-pragma
         args: [--remove]
@@ -24,7 +24,7 @@ repos:
       - id: check-yaml
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
       - id: codespell
         description: Checks for common misspellings.
@@ -41,20 +41,20 @@ repos:
         types: [python]
 
   - repo: https://github.com/psf/black
-    rev: 24.2.0
+    rev: 24.4.2
     hooks:
       - id: black
         types_or: [python, pyi]
         entry: "black"
 
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.3.0
+    rev: v0.4.7
     hooks:
       - id: ruff
         args: ["--fix"]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.8.0
+    rev: v1.10.0
     hooks:
       - id: mypy
         args: [--no-strict-optional, --ignore-missing-imports, --warn-no-return, --explicit-package-bases]

Diff for: bench_data/check_invariant.py

@@ -1,9 +1,14 @@
 import sys
+
 import pandas as pd
 
 
 def check_file(file_name):
-    """Check if the 'start_ts' column is in ascending order and 'end_ts' for a row groups comes before 'start_ts' of the next row group."""
+    """
+    Check if the 'start_ts' column is in ascending order and 'end_ts' for a row
+    groups comes before 'start_ts' of the next row group.
+
+    """
     df = pd.read_csv(file_name)
 
     # Check if 'start_ts' is in ascending order

Diff for: bench_data/extract_groups.py

@@ -1,7 +1,9 @@
+import sys
+
 import pandas as pd
 import pyarrow as pa
 import pyarrow.parquet as pq
-import sys
+
 
 # Define schema for quote ticks
 quote_tick_schema = pa.schema(
@@ -12,15 +14,15 @@
         ("ask_size", pa.uint64()),
         ("ts_event", pa.uint64()),
         ("ts_init", pa.uint64()),
-    ]
+    ],
 )
 
 quote_tick_schema = quote_tick_schema.with_metadata(
     {
         "instrument_id": "EUR/USD.SIM",
         "price_precision": "0",
         "size_precision": "0",
-    }
+    },
 )
 
 trade_tick_schema = pa.schema(
@@ -31,15 +33,15 @@
         ("trade_id", pa.string()),
         ("ts_event", pa.uint64()),
         ("ts_init", pa.uint64()),
-    ]
+    ],
 )
 
 trade_tick_schema = trade_tick_schema.with_metadata(
     {
         "instrument_id": "EUR/USD.SIM",
         "price_precision": "0",
         "size_precision": "0",
-    }
+    },
 )
 
 
@@ -64,7 +66,9 @@ def write_parquet_with_row_group(input_file, output_file, rows_per_row_group):
 
 if __name__ == "__main__":
     if len(sys.argv) < 4:
-        print("Usage: python extract_ts_init.py <parquet_file> <num_rows_per_row_group>")
+        print(
+            "Usage: python extract_ts_init.py <parquet_file> <num_rows_per_row_group>",
+        )
         sys.exit(1)
 
     # Get command-line inputs

Diff for: bench_data/extract_ts_init.py

@@ -1,7 +1,8 @@
-import pyarrow.parquet as pq
 import csv
 import sys
 
+import pyarrow.parquet as pq
+
 
 def extract_ts_init_values(parquet_file, csv_file):
     """Write the first and last 'ts_init' values of each row group to a CSV file."""
@@ -11,7 +12,9 @@ def extract_ts_init_values(parquet_file, csv_file):
     # Open the CSV file for writing
     with open(csv_file, "w", newline="") as csvfile:
         writer = csv.writer(csvfile)
-        writer.writerow(["index", "start_ts", "end_ts", "group_size"])  # Write the header
+        writer.writerow(
+            ["index", "start_ts", "end_ts", "group_size"],
+        )  # Write the header
 
         # Iterate over each row group in the Parquet file
         for i in range(parquet_file.num_row_groups):

Diff for: bench_data/gen_data_stats.py

@@ -1,6 +1,7 @@
-import sys
-import os
 import csv
+import os
+import sys
+
 import pyarrow.parquet as pq
 
 
@@ -9,7 +10,7 @@ def record_data_stats(folder_path, csv_file):
     with open(csv_file, "w", newline="") as csvfile:
         writer = csv.writer(csvfile)
         writer.writerow(
-            ["file_name", "file_size_kb", "total_rows", "max_row_group_size"]
+            ["file_name", "file_size_kb", "total_rows", "max_row_group_size"],
         )  # Write the header
 
         # Walk the folder
@@ -34,7 +35,9 @@ def record_data_stats(folder_path, csv_file):
                         max_row_group_size = max(max_row_group_size, num_rows)
 
                     # Write the statistics to the CSV file
-                    writer.writerow([file_path, file_size_kb, total_rows, max_row_group_size])
+                    writer.writerow(
+                        [file_path, file_size_kb, total_rows, max_row_group_size],
+                    )
 
 
 if __name__ == "__main__":

Diff for: nautilus_data/hist_data_to_catalog.py

@@ -15,8 +15,8 @@
 
 from os import PathLike
 from pathlib import Path
-import requests
 
+import requests
 from nautilus_trader.persistence.catalog import ParquetDataCatalog
 from nautilus_trader.persistence.wranglers import QuoteTickDataWrangler
 from nautilus_trader.test_kit.providers import CSVTickDataLoader
@@ -36,7 +36,11 @@ def load_fx_hist_data(
     instrument = TestInstrumentProvider.default_fx_ccy(currency)
     wrangler = QuoteTickDataWrangler(instrument)
 
-    df = CSVTickDataLoader.load(filename, index_col=0, datetime_format="%Y%m%d %H%M%S%f")
+    df = CSVTickDataLoader.load(
+        filename,
+        index_col=0,
+        datetime_format="%Y%m%d %H%M%S%f",
+    )
     df.columns = ["bid_price", "ask_price", "size"]
     print(df)